© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25836
    Prev
    Next
    INDEX
    Explanations

    numerically significant financial data and statistics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    Manbalar
    -0.69
     ſay
    -0.54
     ſhall
    -0.53
     ſhould
    -0.52
     Francine
    -0.50
    Personendaten
    -0.50
     rapid
    -0.49
    findFirst
    -0.48
    apd
    -0.48
     becauſe
    -0.48
    POSITIVE LOGITS
     disponibilités
    0.84
     surla
    0.63
    dyti
    0.63
    AddHtmlAttribute
    0.63
    DockStyle
    0.60
     enctype
    0.58
    IntoConstraints
    0.58
     المعيارى
    0.58
     Vikipedi
    0.57
     виправивши
    0.57
    Activations Density 0.047%

    No Known Activations